BigFoot Networks Killer NIC: Killer Marketing or Killer Product?
by Gary Key on October 31, 2006 2:00 AM EST- Posted in
- Networking
Killer NIC Technology
Hopefully you are still with us after the previous segment as writing it was better than taking a dose of Lunesta. In all seriousness, the technology of offloading network transactions to a dedicated processor has proven to be very beneficial in the corporate server environment. The typical TNIC is designed to handle data payloads that are larger than 8KB and in certain instances will have reduced performance (lower throughput and higher latencies) with smaller and more frequent data payloads in the 1KB to 4KB range. This range is what most messaging traffic, web services, and real-time data applications such as games utilize at this time. TNICs are generally optimized for TCP (transmission control protocol) packets where the vast majority of games today utilize UDP (user datagram protocol) packets for data transmission.
The differences between the two protocols are numerous but we will hit the highlights. TCP has a standard header length of twenty bytes versus eight for UDP. The normal TCP header will contain metric information such as sequence and acknowledgement numbers along with a requirement for a checksum number. UDP packets do not include metrics and the checksum information is optional. In other words, UDP does not provide the reliability, security, or ordering (queue) guarantees that TCP can deliver. The datagrams in the UDP packet may arrive out order or not at all and your system or application may never notice. Unlike TCP, UDP provides no guarantees for delivery or proper queuing, so why use it? The answer is simple: UDP is faster and far more efficient for time sensitive applications such as gaming, and you don't need every data packet to game properly. (I.e., if you miss one packet that says player X is at coordinates (10,10,15) but you get the next packet that shows X at (12,11,15), the missing packet will not seriously impact the overall experience unless of course you missed a shot or took one.) With this simple premise in mind BigFoot Networks decided to take TOE technology and design a TNIC that focused on UDP protocols and latency reduction.
The main technology focus of BigFoot Networks is centered on their LLR technology. LLR (Lag and Latency Reduction) technology that implements a 1-packet 1-interrupt model to eliminate the entire queuing and buffering operations standard NICs do during the packet receipt and transmission process. When in game mode, the Killer NIC will also completely bypass the Windows networking stack which contributes to further latency or lag reductions depending upon the application. When BigFoot Networks discusses ping improvements in games they are not talking about reducing ping through your network or at the server. This is completely out of their control and although their marketing information is not clear about it the reduction in ping comes on the host machine. These reductions come from bypassing the Windows Network Stack while in Game mode. Depending upon the application and packet size there is generally a 1~3ms delay due to system buffering and another 3~10ms delay in the queuing and processing of data packets in the current Windows Network Stack.
What makes LLR work is the NPU (network processing unit) on the card. This processor powers both the Windows Network Stack bypass engine and the 1-packet 1-interrupt model. In short, this NPU gets the normal network transactions out of the graphics path in games. This can result in improvements in FPS (frames per second) and reduced lag. With a standard network card, before nearly every graphics frame is drawn, there is first a check to the server to see if a new data packet has arrived or if one needs to be sent. Checking the server for new data packets can use up processor clock cycles whether or not data is there. Instead of a multitude of interrupts as we discussed earlier, the Killer NIC will receive or send those data packets in a single instruction. The Killer NIC has the further ability of interrupting the game directly when new data arrives. The Killer NIC is designed around reducing latencies and not throughput.
While LLR technology is impressive to some degree we have to temper any enthusiasm with the fact that most games are designed very differently in their handling of network tasks. Some games do not check for new network data on every graphics frame so any FPS improvements will be minimal at best or completely nonexistent the majority of time. Several older games do not use UDP packets so performance could suffer as the Network Stack bypass model is not used and the card must act as standard NIC. The one thing that we have learned during testing is that many games do not report accurate latency (ping rates) so any improvements are not as measurable but at times can be felt do to smoother game play. The basic TOE and TNIC technology still applies to this card and has been proven over the past few years in the corporate server environment. Converting this technology to the desktop with the added spin of improving gaming is certainly an admirable feat but how well does it work? We will answer that question in a few pages but first let's take a look at the obligatory marketing information.
Hopefully you are still with us after the previous segment as writing it was better than taking a dose of Lunesta. In all seriousness, the technology of offloading network transactions to a dedicated processor has proven to be very beneficial in the corporate server environment. The typical TNIC is designed to handle data payloads that are larger than 8KB and in certain instances will have reduced performance (lower throughput and higher latencies) with smaller and more frequent data payloads in the 1KB to 4KB range. This range is what most messaging traffic, web services, and real-time data applications such as games utilize at this time. TNICs are generally optimized for TCP (transmission control protocol) packets where the vast majority of games today utilize UDP (user datagram protocol) packets for data transmission.
The differences between the two protocols are numerous but we will hit the highlights. TCP has a standard header length of twenty bytes versus eight for UDP. The normal TCP header will contain metric information such as sequence and acknowledgement numbers along with a requirement for a checksum number. UDP packets do not include metrics and the checksum information is optional. In other words, UDP does not provide the reliability, security, or ordering (queue) guarantees that TCP can deliver. The datagrams in the UDP packet may arrive out order or not at all and your system or application may never notice. Unlike TCP, UDP provides no guarantees for delivery or proper queuing, so why use it? The answer is simple: UDP is faster and far more efficient for time sensitive applications such as gaming, and you don't need every data packet to game properly. (I.e., if you miss one packet that says player X is at coordinates (10,10,15) but you get the next packet that shows X at (12,11,15), the missing packet will not seriously impact the overall experience unless of course you missed a shot or took one.) With this simple premise in mind BigFoot Networks decided to take TOE technology and design a TNIC that focused on UDP protocols and latency reduction.
The main technology focus of BigFoot Networks is centered on their LLR technology. LLR (Lag and Latency Reduction) technology that implements a 1-packet 1-interrupt model to eliminate the entire queuing and buffering operations standard NICs do during the packet receipt and transmission process. When in game mode, the Killer NIC will also completely bypass the Windows networking stack which contributes to further latency or lag reductions depending upon the application. When BigFoot Networks discusses ping improvements in games they are not talking about reducing ping through your network or at the server. This is completely out of their control and although their marketing information is not clear about it the reduction in ping comes on the host machine. These reductions come from bypassing the Windows Network Stack while in Game mode. Depending upon the application and packet size there is generally a 1~3ms delay due to system buffering and another 3~10ms delay in the queuing and processing of data packets in the current Windows Network Stack.
What makes LLR work is the NPU (network processing unit) on the card. This processor powers both the Windows Network Stack bypass engine and the 1-packet 1-interrupt model. In short, this NPU gets the normal network transactions out of the graphics path in games. This can result in improvements in FPS (frames per second) and reduced lag. With a standard network card, before nearly every graphics frame is drawn, there is first a check to the server to see if a new data packet has arrived or if one needs to be sent. Checking the server for new data packets can use up processor clock cycles whether or not data is there. Instead of a multitude of interrupts as we discussed earlier, the Killer NIC will receive or send those data packets in a single instruction. The Killer NIC has the further ability of interrupting the game directly when new data arrives. The Killer NIC is designed around reducing latencies and not throughput.
While LLR technology is impressive to some degree we have to temper any enthusiasm with the fact that most games are designed very differently in their handling of network tasks. Some games do not check for new network data on every graphics frame so any FPS improvements will be minimal at best or completely nonexistent the majority of time. Several older games do not use UDP packets so performance could suffer as the Network Stack bypass model is not used and the card must act as standard NIC. The one thing that we have learned during testing is that many games do not report accurate latency (ping rates) so any improvements are not as measurable but at times can be felt do to smoother game play. The basic TOE and TNIC technology still applies to this card and has been proven over the past few years in the corporate server environment. Converting this technology to the desktop with the added spin of improving gaming is certainly an admirable feat but how well does it work? We will answer that question in a few pages but first let's take a look at the obligatory marketing information.
Facebook
Twitter
RSS
87 Comments
View All Comments
Gary Key - Wednesday, November 1, 2006 - link
We tested these two cards as part of our Killer NIC testing routine. We did not report the numbers as they did not vary greatly from the NIVIDA 590SLI NIC solution.Crassus - Wednesday, November 1, 2006 - link
Sorry, but that plus the server test would have been very useful information I would have liked in the review. Or maybe we can have a different review, sort of a "NIC roundup". If your results are the same across the board, it's a finding worth mentioning as well, isn't it?Frumious1 - Tuesday, October 31, 2006 - link
I bet it doesn't even beat the onboard NVIDIA NIC. Or rather, it will tie the NVIDIA solution, which means it's equal to the Killer in most situations and fractionally slower in a few games. Maybe it has lower CPU usage when doing gigabit transmits, but high bandwidth with low CPU usage isn't going to matter much for gaming. Not that any NIC related stuff matters much for gaming these days.vaystrem - Tuesday, October 31, 2006 - link
I agree its very difficult to test NIC performance and kudos to Anandtech for trying. But, it seems to me that using the card as a server for the games where it saw the most improvement, Fear/CS, and even for those that it didn't may be more enlightening than exploring the client side of things.Gary Key - Tuesday, October 31, 2006 - link
We set up one of our test beds as a server for a couple of the games we tested. The performance was actually worse than our NVIDIA NIC (dualnet/teaming), Intel PRO/1000 PT, and barely did better than our D-Link PCI NIC in half of the tests. We will not fault the card for its peformance since it was specifically designed as a client side card. This very well could change in the future due to their ability to optimize driver code on the FPGA unit. The article could have gone another five pages with the server and LAN tests that we completed (neither showed any significant differences). It appears from several of the comments that anything over three pages was a waste anyway. ;-)EODetroit - Tuesday, October 31, 2006 - link
Except according to the PR material the card is made for game clients, not optimized for game servers.VooDooAddict - Tuesday, October 31, 2006 - link
While the POSIBILITY of embeded linux apps is interesting. For someone who would have the $$ do buy this ... they would have the money to put inexpensive PC parts together into a linux machine. Likely they have spare parts leftover from thier last upgrade.Anyone else think the company name is strangly fitting? "BigFoot" ... Myth and Hype?
Certainly not saying a nice NIC isnt'a good investment ... but at almost $300 ... it's a joke. Drop the embedded linux, hit the $50 price point and this thing would probably sell like mad to WoW Addicts. (eventually also have a PCIe version)
The aegia(sp?) physics processor is the same way. Great concept, but the tangable benefits are so minimal for the price. $300 Video cards took off because there was a tangable benefit.
Dropping anothre $300 into the Storage System, Monitor, CPU, Video card, RAM, or even Audio system (surround speakers) would give one a much mroe imersive experience.
Someone made the wrong decission to stick with the embedded linux thing. Seriously a sperate leftover parts Linux box and a DLINK 4100 router would be a far better way to go.
So any guesses as to the next $300 (*caugh* gimic *caugh*) expendature to "improve" gaming?
For those comparing this to SLI/Crossfire. SLI and Crossfire can offer substantial image quality enhancements for people with large pixel count LCDs. The ability to run LCDs at native resolution for gaming is a very tangable benefit. Not something everyone agrees it worth the $$. But the benefit is there.
VooDooAddict - Tuesday, October 31, 2006 - link
I was really hoping for somethign major from this card ... just from the perspective of reliving history.Around 10 years ago now (back around '96-'97) when NICs weren't build onboard spending $60-$70 on a 3Com 3c905 or a server class Intel NIC would make a bug differance in overall system performace when working with the Internet, LAN, and Gaming. They gave me big advantages over anyone who just went out an bought a cheapo $20 NE2000 comptable NIC (16-bit ISA even!).
I'm talking Quake 1, Duke3D, Quake 2, Quake CTF, Original Unreal... A single 3dFx VooDooGraphics Board + 3c905 = pwnage (back when "pwnage" was still a typo). I was so often accused of cheating by laptop wielding, software emulating, newbies (wasn't spelt "noob" then).
... That above is why I picked up the handle "VooDooAddict"
EODetroit - Tuesday, October 31, 2006 - link
And they deleted it. Claiming it needed to be moved from "Testimonials" to "General" forum. Whatever, but they didn't actually move my post, they deleted it and replaced it with a post of their own, with the link, plus quoted all the good things said in the Anandtech review and none of the bad. Typical and misleading, but hey, its their web site. They can do what they want. Still, misleading people doesn't endear them to anyone.LoneWolf15 - Tuesday, October 31, 2006 - link
I admire the amount of engineering that went into this product. It's obvious that the product isn't "snake oil" in the same way that, say, SoftRAM software was back in the day. There's a lot more to this card than just a NIC.That said, I don't think it provides enough benefit to justify $279 (unless perhaps you're making $50k+ a year in the PGL). Today's NICs are already pretty well optimized for most situations, plus many mainboard NICS are directly on the PCIe bus, something the Killer NIC can't offer (and as someone pointed out, try doing gig ethernet across a PCI slot; it really isn't feasible, especially if you already have the PCI bus shared with other components like a TV tuner or sound card). The Killer NIC's most interesting feature, FNApps, is not useful at the moment, and I'm still concerned that it might pose a security risk through a malformed application (that's assuming someone coded that app in the first place, considering how little marketshare the Killer NIC is likely to have). Like the Ageia PhysX, at this point in time, I don't see the justification.
P.S. Is it just me, or does the heatsink "K" look like a Klingon weapon? I'm thinking either Klingon brass-knuckles or a hybrid bat-lef. ;)